Younyoung Choi

Prof. Younyoung Choi

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 April 2019 in Psychiatry Investigation
Verified
Journal Article
Open access
PDF file
GCGyeongcheol Cho
Gyeongcheol Cho
JYJinyeong Yim
Jinyeong Yim
YCYounyoung Choi
Younyoung Choi
JKJungmin Ko
Jungmin Ko
SLSeoung-Hwan Lee
Seoung-Hwan Lee
Enhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice. Researches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized. Based on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics. Researchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.

19 November 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YCYounyoung Choi
Younyoung Choi
CMCayce McClenen
Cayce McClenen
Online formative assessments in e-learning systems are increasingly of interest in the field of education. While substantial research into the model and item design aspects of formative assessment has been conducted, few software systems embodied with a psychometric model have been proposed to allow us to adaptively implement formative assessments. This study aimed to develop an adaptive formative assessment system, called computerized formative adaptive testing (CAFT) by using artificial intelligence methods based on computerized adaptive testing (CAT) and Bayesian networks as learning analytics. CAFT can adaptively administer personalized formative assessment to a learner by dynamically selecting appropriate items and tests aligned with the learner’s ability. Forty items in an item bank were evaluated by 410 learners, moreover, 1000 learners were recruited for a simulation study and 120 learners were enrolled to evaluate the efficiency, validity, and reliability of CAFT in an application study. The results showed that, through CAFT, learners can adaptively take item s and tests in order to receive personalized diagnostic feedback about their learning progression. Consequently, this study highlights that a learning management system which integrates CAT as an artificially intelligent component is an efficient educational evaluation tool for a remote personalized learning service.

4 August 2022 in Management International Review
Verified
Journal Article
Closed access
PDF file
GCGyeongcheol Cho
Gyeongcheol Cho
CSChristopher Schlaegel
Christopher Schlaegel
HHHeungsun Hwang
Heungsun Hwang
YCYounyoung Choi
Younyoung Choi
MSMarko Sarstedt
Marko Sarstedt
CRChristian M. Ringle
Christian M. Ringle

YCYounyoung Choi
Younyoung Choi
HLHyunwoo Lee
Hyunwoo Lee
(1) Background: A learner’s cognitive load in a learning system should be effectively addressed to provide optimal learning processing because the cognitive load explains individual learning differences. However, little empirical research has been conducted into the validation of a cognitive load measurement tool (cognitive load scale, i.e., CLS) suited to online learning systems within higher education. The purpose of this study was to evaluate the psychometric properties of the CLS in an online learning system within higher education through the framework suggested by the Standards for Educational and Psychological Testing. (2) Methods: Data from 800 learners were collected from a cyber-university in South Korea. The age of students ranged from 20 to 64. The CLS was developed, including three components: extraneous cognitive load, intrinsic cognitive load, and germane cognitive load. Then, psychometric properties of the CLS were evaluated including reliability and validity. Evidence relating to content validity, construct validity, and criterion validity were collected. The response pattern of each item was evaluated on the basis of item response theory (IRT). Cronbach’s α was computed for reliability. (3) Results: The CLS presented high internal consistency. A three-factor model with extraneous cognitive load, intrinsic cognitive load, and germane cognitive load was suggested by exploratory and confirmatory factor analysis. This three-factor model is consistent with the previous research into the cognitive load in an offline learning environment. Higher levels of the extraneous cognitive load and intrinsic cognitive load were related to lower levels of academic achievement in an online learning environment, but the germane cognitive load was not significantly positively associated with midterm exam scores, though it was significantly related to the final exam scores. IRT analysis showed that the item-fit statistics for all items were acceptable. Lastly, the measurement invariance was examined through differential item functioning analysis (DIF), with the results suggesting that the items did not contain measurement variance in terms of gender. (4) Conclusions: This validation study of the CLS in an online learning environment within higher education assesses psychometric properties and suggests that the CLS is valid and reliable with a three-factor model. There is a need for an evaluation tool to take into account the cognitive load among learners in online learning system because the characteristics of learners within higher education were varied. This CLS will help instructional/curriculum designers and educational instructors to provide more effective instructions and identify individual learning differences in an online learning environment within higher education.

25 November 2018 in Psychiatry Investigation
Verified
Journal Article
Open access
PDF file
YKYeseul Kim
Yeseul Kim
YPYeonsoo Park
Yeonsoo Park
GCGyeongcheol Cho
Gyeongcheol Cho
KPKiho Park
Kiho Park
SKShin-Hyang Kim
Shin-Hyang Kim
KCKee-Hong Choi
Kee-Hong Choi
This study evaluated the psychometric properties of the Korean Anxiety Screening Assessment (K-ANX) developed for screening anxiety disorders. Data from 613 participants were analyzed. The K-ANX was evaluated for reliability using Cronbach's alpha, item-total correlation, and test information curve, and for validity using focus group interviews, factor analysis, correlational analysis, and item characteristics based on item response theory (IRT). The diagnostic sensitivity and specificity of the K-ANX were compared with those of the Beck Anxiety Inventory (BAI) and Generalized Anxiety Disorder 7-item scale (GAD-7). The K-ANX showed excellent internal consistency (α=0.97) and item-total coefficients (0.92-0.97), and a one-factor structure was suggested. All items were highly correlated with the total scores of the BAI, GAD-7, and Penn State Worry Questionnaire. IRT analysis indicated the K-ANX was most informative as a screening tool for anxiety disorders at the range between 0.8 and 1.6 (i.e., top 21.2 to 5.5 percentiles). Higher sensitivity (0.795) and specificity (0.937) for identifying anxiety disorders were observed in the K-ANX compared to the BAI and GAD-7. The K-ANX is a reliable and valid measure to screen anxiety disorders in a Korean sample, with greater sensitivity and specificity than current measures of anxiety symptoms.

10 September 2021 in Sustainability
Verified
Journal Article
Open access
PDF file
YCYounyoung Choi
Younyoung Choi
JKJi Geun Kim
Ji Geun Kim
A learner’s cognitive load is highly associated with their academic achievement within learning systems. Diagnostic information about a learner’s cognitive load is useful for achieving optimal learning, by enabling the learner to manage and control their cognitive load in the e-learning environment. However, little empirical research has been conducted to obtain diagnostic information about the cognitive load in e-learning systems. The purpose of this study was to analyze a personalized diagnostic evaluation for a learner’s cognitive load in an e-learning system, using the Bayesian Network (BN) as a learning analytic method. Data from 700 learners were collected from Cyber University. A learner’s cognitive load level was measured in terms of three components: extraneous cognitive load, intrinsic cognitive load, and germane cognitive load. The BN was built by representing the relationship among the extraneous cognitive load, intrinsic cognitive load, germane cognitive load, and academic achievement. The conditional and marginal probabilities in the BN were estimated. This study found that the BN provided diagnostic information about a learner’s level of cognitive load in the e-learning system. In addition, the BN predicted the learner’s academic achievement in terms of their different cognitive load patterns. This study’s results imply that diagnostic information related to cognitive load helps learners to improve academic achievement by managing and controlling their cognitive loads in the e-learning environment. In addition, instructional designers are able to offer more appropriately customized instructional methods by considering learners’ cognitive loads in online learning.